Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3502 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1669. Min Act: -0.0002

Data Index: 591755 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1470. Min Act: -0.0002

Data Index: 1184764 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1357. Min Act: -0.0002

Data Index: 674878 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1105. Min Act: -0.0002

Data Index: 313069 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1167. Min Act: -0.0002

Data Index: 944109 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1165. Min Act: -0.0002

Data Index: 122744 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0994. Min Act: -0.0002

Data Index: 829796 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1047. Min Act: -0.0002

Data Index: 738860 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1055. Min Act: -0.0002

Data Index: 626363 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1094. Min Act: -0.0002

Data Index: 974446 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1087. Min Act: -0.0002

Data Index: 682054 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0992. Min Act: -0.0002

Data Index: 190556 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1327185 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0991. Min Act: -0.0002

Data Index: 369055 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1005040 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1156292 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1219127 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1016. Min Act: -0.0002

Data Index: 345200 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0920. Min Act: -0.0002

Data Index: 996846 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1001. Min Act: -0.0002

Data Index: 995990 (C4 (Web Text))

Max Activating Token Index: 142